Search

Face Recognition Systems (FRS) have increasingly integrated into critical applications, including surveillance and user authentication, highlighting their pivotal role in modern security systems. Recent studies have revealed vulnerabilities in FRS to adversarial (e.g., adversarial patch attacks) and backdoor attacks (e.g., training data poisoning), raising significant concerns about their reliability and trustworthiness. Previous studies primarily focus on traditional adversarial or backdoor attacks, overlooking the resource-intensive or privileged-manipulation nature of such threats, thus limiting their practical generalization, stealthiness, universality and robustness. Correspondingly, in this paper, we delve into the inherent vulnerabilities in FRS through user studies and preliminary explorations. By exploiting these vulnerabilities, we identify a novel attack, facial identity backdoor attack dubbed FIBA, which unveils a potentially more devastating threat against FRS:an enrollment-stage backdoor attack. FIBA circumvents the limitations of traditional attacks, enabling broad-scale disruption by allowing any attacker donning a specific trigger to bypass these systems. This implies that after a single, poisoned example is inserted into the database, the corresponding trigger becomes a universal key for any attackers to spoof the FRS. This strategy essentially challenges the conventional attacks by initiating at the enrollment stage, dramatically transforming the threat landscape by poisoning the feature database rather than the training data., Comment: 19 pages,version 3

Recent language models have demonstrated proficiency in summarizing source code. However, as in many other domains of machine learning, language models of code lack sufficient explainability. Informally, we lack a formulaic or intuitive understanding of what and how models learn from code. Explainability of language models can be partially provided if, as the models learn to produce higher-quality code summaries, they also align in deeming the same code parts important as those identified by human programmers. In this paper, we report negative results from our investigation of explainability of language models in code summarization through the lens of human comprehension. We measure human focus on code using eye-tracking metrics such as fixation counts and duration in code summarization tasks. To approximate language model focus, we employ a state-of-the-art model-agnostic, black-box, perturbation-based approach, SHAP (SHapley Additive exPlanations), to identify which code tokens influence that generation of summaries. Using these settings, we find no statistically significant relationship between language models' focus and human programmers' attention. Furthermore, alignment between model and human foci in this setting does not seem to dictate the quality of the LLM-generated summaries. Our study highlights an inability to align human focus with SHAP-based model focus measures. This result calls for future investigation of multiple open questions for explainable language models for code summarization and software engineering tasks in general, including the training mechanisms of language models for code, whether there is an alignment between human and model attention on code, whether human attention can improve the development of language models, and what other model focus measures are appropriate for improving explainability.

Neural code summarization leverages deep learning models to automatically generate brief natural language summaries of code snippets. The development of Transformer models has led to extensive use of attention during model design. While existing work has primarily and almost exclusively focused on static properties of source code and related structural representations like the Abstract Syntax Tree (AST), few studies have considered human attention, that is, where programmers focus while examining and comprehending code. In this paper, we develop a method for incorporating human attention into machine attention to enhance neural code summarization. To facilitate this incorporation and vindicate this hypothesis, we introduce EyeTrans, which consists of three steps: (1) we conduct an extensive eye-tracking human study to collect and pre-analyze data for model training, (2) we devise a data-centric approach to integrate human attention with machine attention in the Transformer architecture, and (3) we conduct comprehensive experiments on two code summarization tasks to demonstrate the effectiveness of incorporating human attention into Transformers. Integrating human attention leads to an improvement of up to 29.91% in Functional Summarization and up to 6.39% in General Code Summarization performance, demonstrating the substantial benefits of this combination. We further explore performance in terms of robustness and efficiency by creating challenging summarization scenarios in which EyeTrans exhibits interesting properties. We also visualize the attention map to depict the simplifying effect of machine attention in the Transformer by incorporating human attention. This work has the potential to propel AI research in software engineering by introducing more human-centered approaches and data.

The rise of advanced persistent threats (APTs) has marked a significant cybersecurity challenge, characterized by sophisticated orchestration, stealthy execution, extended persistence, and targeting valuable assets across diverse sectors. Provenance graph-based kernel-level auditing has emerged as a promising approach to enhance visibility and traceability within intricate network environments. However, it still faces challenges including reconstructing complex lateral attack chains, detecting dynamic evasion behaviors, and defending smart adversarial subgraphs. To bridge the research gap, this paper proposes an efficient and robust APT defense scheme leveraging provenance graphs, including a network-level distributed audit model for cost-effective lateral attack reconstruction, a trust-oriented APT evasion behavior detection strategy, and a hidden Markov model based adversarial subgraph defense approach. Through prototype implementation and extensive experiments, we validate the effectiveness of our system. Lastly, crucial open research directions are outlined in this emerging field., Comment: This work has been accepted by IEEE NETWORK in April 2024. 9 pages, 5 figures, 1 table

Advanced persistent threat (APT) is a kind of stealthy, sophisticated, and long-term cyberattack that has brought severe financial losses and critical infrastructure damages. Existing works mainly focus on APT defense under stable network topologies, while the problem under time-varying dynamic networks (e.g., vehicular networks) remains unexplored, which motivates our work. Besides, the spatiotemporal dynamics in defense resources, complex attackers' lateral movement behaviors, and lack of timely defense make APT defense a challenging issue under time-varying networks. In this paper, we propose a novel game-theoretical APT defense approach to promote real-time and optimal defense strategy-making under both periodic time-varying and general time-varying environments. Specifically, we first model the interactions between attackers and defenders in an APT process as a dynamic APT repair game, and then formulate the APT damage minimization problem as the precise prevention and control (PPAC) problem. To derive the optimal defense strategy under both latency and defense resource constraints, we further devise an online optimal control-based mechanism integrated with two backtracking-forward algorithms to fastly derive the near-optimal solution of the PPAC problem in real time. Extensive experiments are carried out, and the results demonstrate that our proposed scheme can efficiently obtain optimal defense strategy in 54481 ms under seven attack-defense interactions with 9.64$\%$ resource occupancy in stimulated periodic time-varying and general time-varying networks. Besides, even under static networks, our proposed scheme still outperforms existing representative APT defense approaches in terms of service stability and defense resource utilization.

Due to the limited battery and computing resource, offloading unmanned aerial vehicles (UAVs)' computation tasks to ground infrastructure, e.g., vehicles, is a fundamental framework. Under such an open and untrusted environment, vehicles are reluctant to share their computing resource unless provisioning strong incentives, privacy protection, and fairness guarantee. Precisely, without strategy-proofness guarantee, the strategic vehicles can overclaim participation costs so as to conduct market manipulation. Without the fairness provision, vehicles can deliberately abort the assigned tasks without any punishments, and UAVs can refuse to pay by the end, causing an exchange dilemma. Lastly, the strategy-proofness and fairness provision typically require transparent payment/task results exchange under public audit, which may disclose sensitive information of vehicles and make the privacy preservation a foremost issue. To achieve the three design goals, we propose SEAL, an integrated framework to address strategy-proof, fair, and privacy-preserving UAV computation offloading. SEAL deploys a strategy-proof reverse combinatorial auction mechanism to optimize UAVs' task offloading under practical constraints while ensuring economic-robustness and polynomial-time efficiency. Based on smart contracts and hashchain micropayment, SEAL implements a fair on-chain exchange protocol to realize the atomic completion of batch payments and computing results in multi-round auctions. In addition, a privacy-preserving off-chain auction protocol is devised with the assistance of the trusted processor to efficiently protect vehicles' bid privacy. Using rigorous theoretical analysis and extensive simulations, we validate that SEAL can effectively prevent vehicles from manipulating, ensure privacy protection and fairness, improve the offloading efficiency., Comment: Accepted by IEEE Transactions on Information Forensics and Security (IEEE TIFS)

There has been an increasing interest in modeling continuous-time dynamics of temporal graph data. Previous methods encode time-evolving relational information into a low-dimensional representation by specifying discrete layers of neural networks, while real-world dynamic graphs often vary continuously over time. Hence, we propose Continuous Temporal Graph Networks (CTGNs) to capture the continuous dynamics of temporal graph data. We use both the link starting timestamps and link duration as evolving information to model the continuous dynamics of nodes. The key idea is to use neural ordinary differential equations (ODE) to characterize the continuous dynamics of node representations over dynamic graphs. We parameterize ordinary differential equations using a novel graph neural network. The existing dynamic graph networks can be considered as a specific discretization of CTGNs. Experiment results on both transductive and inductive tasks demonstrate the effectiveness of our proposed approach over competitive baselines.